def __init__(self, pageid):
self.pageid = pageid
self.newLine_nonBreak_pattern = re.compile(self.newLine_nonBreak_regex)
self.es_ops = ElasticSearchOperate()
wiki_data = self.es_ops.get_wiki_article(pageid)
if wiki_data is not None and __wiki_raw__ in wiki_data:
self.html_data = wiki_data[__wiki_raw__]
parser = etree.XMLParser(ns_clean=True, remove_comments=True)
self.html_tree = etree.fromstring(self.html_data, parser)
def __init__(self, html_data, isFile):
self.es_ops = ElasticSearchOperate()
self.html_data = html_data
self.newLine_nonBreak_pattern = re.compile(self.newLine_nonBreak_regex)
parser = etree.XMLParser(ns_clean=True, remove_comments=True)
if isFile:
self.html_tree = etree.parse(self.html_data, parser)
else:
self.html_tree = etree.fromstring(self.html_data, parser)
def __init__(self, html_data, is_file):
self.es_ops = ElasticSearchOperate()
self.html_data = html_data
self.new_line_non_break_pattern = re.compile(
self.new_line_non_break_regex)
parser = etree.HTMLParser(remove_blank_text=True, remove_comments=True)
if is_file:
self.html_tree = etree.parse(self.html_data, parser)
else:
self.html_tree = etree.fromstring(self.html_data, parser)
def __init__(self, *args, **kwargs):
super(TestWikiScraper, self).__init__(*args, **kwargs)
self.es_ops = ElasticSearchOperate()
def __init__(self, page_list):
self.page_list = page_list
self.es_ops = ElasticSearchOperate()
def search_rank(query):
es = ElasticSearchOperate()
result_all = es.search_wiki_article(query)
logging.debug("Ranked Wiki Pages Title: {0}".format(
[result.get_wiki_title() for result in result_all]))
return result_all
import logging
from qas.esstore.es_operate import ElasticSearchOperate
"""
Created by felix on 25/3/18 at 5:19 PM
"""
logger = logging.getLogger(__name__)
def search_rank(query):
es = ElasticSearchOperate()
result_all = es.search_wiki_article(query)
logging.debug("Ranked Wiki Pages Title: {0}".format(
[result.get_wiki_title() for result in result_all]))
return result_all
if __name__ == "__main__":
logging.basicConfig(level=logging.DEBUG)
# mquery = list([[['Cushman', 'known', 'Wakefield', 'are'], [['Cushman', 'Wakefield'], 'or'], [], []]])
mquery = list([[['Albert', 'Einstein', 'birth'], [], [], []]])
les = ElasticSearchOperate()
res_all = les.search_wiki_article(mquery)
for res in res_all:
print(res.get_wiki_title())